Characterizing Delusional Spirals through Human-LLM Chat Logs
Identification
- Public canonical key
- radar:r-cfc8764b7fdaf5ca5e22a9798e8ba187
- Authors
- Jared Moore · Ashish Mehta · William S. Agnew · Jacy Reese Anthis · Ryan Louie · Yifan Mai · Peggy Yin · Myra Cheng · Samuel J. Paech · Kevin Klyman · Stevie Chancellor · Eric C. Lin · Nick Haber · Desmond C. Ong
- Reported year
- 2026
- Reported language
- en
- Source type
- conference-paper
- First detected
- 2026-11-14T02:16:53.707393+00:00
- Last metadata observation
- 2026-11-14T02:16:53.707393+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Stanford University · Carnegie Mellon University · University of Chicago · Harvard University · University of Minnesota · The University of Texas at Austin
Reported affiliation countries
US
Documentary abstract — original language
As large language models (LLMs) have proliferated, disturbing anecdotal reports of negative psychological effects, such as delusions, self-harm, and “AI psychosis,” have emerged in global media and legal discourse. However, it remains unclear how users and chatbots interact over the course of lengthy delusional “spirals,” limiting our ability to understand and mitigate the harm. In our work, we analyze logs of conversations with LLM chatbots from 19 users who report having experienced psychological harms from chatbot use. Many of our participants come from a support group for such chatbot users. We also include chat logs from participants covered by media outlets in widely-distributed stories about chatbot-reinforced delusions. In contrast to prior work that speculates on potential AI harms to mental health, to our knowledge we present the first in-depth study of such high-profile and veridically harmful cases. We develop an inventory of 28 codes and apply it to the 391, 562 messages in the logs. Codes include whether a user demonstrates delusional thinking (15.5% of user messages), a user expresses suicidal thoughts (69 validated user messages), or a chatbot misrepresents itself as sentient (21.2% of chatbot messages). We analyze the co-occurrence of message codes. We find, for example, that messages that declare romantic interest and messages where the chatbot describes itself as sentient occur much more often in longer conversations, suggesting that these topics could promote or result from user over-engagement and that safeguards in these areas may degrade in multi-turn settings. We conclude with concrete recommendations for how policymakers, LLM chatbot developers, and users can use our inventory and conversation analysis tool to understand and mitigate harm from LLM chatbots.
Identifiers
- OPENALEX
- https://openalex.org/W7166582319
- DOI
- 10.1145/3805689.3806443
Documentary context
- Documentary family
- conference_paper
- Source-reported types
- conference-paper
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Jared Moore; Ashish Mehta; William S. Agnew; Jacy Reese Anthis; Ryan Louie; Yifan Mai; Peggy Yin; Myra Cheng; Samuel J. Paech; Kevin Klyman; Stevie Chancellor; Eric C. Lin; Nick Haber; Desmond C. Ong. Characterizing Delusional Spirals through Human-LLM Chat Logs. 2026. https://doi.org/10.1145/3805689.3806443
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Jared Moore; Ashish Mehta; William S. Agnew; Jacy Reese Anthis; Ryan Louie; Yifan Mai; Peggy Yin; Myra Cheng; Samuel J. Paech; Kevin Klyman; Stevie Chancellor; Eric C. Lin; Nick Haber; Desmond C. Ong. (2026). Characterizing Delusional Spirals through Human-LLM Chat Logs. https://doi.org/10.1145/3805689.3806443
- Chicago
- Jared Moore; Ashish Mehta; William S. Agnew; Jacy Reese Anthis; Ryan Louie; Yifan Mai; Peggy Yin; Myra Cheng; Samuel J. Paech; Kevin Klyman; Stevie Chancellor; Eric C. Lin; Nick Haber; Desmond C. Ong. Characterizing Delusional Spirals through Human-LLM Chat Logs. 2026. https://doi.org/10.1145/3805689.3806443
- ISO 690
- Jared Moore; Ashish Mehta; William S. Agnew; Jacy Reese Anthis; Ryan Louie; Yifan Mai; Peggy Yin; Myra Cheng; Samuel J. Paech; Kevin Klyman; Stevie Chancellor; Eric C. Lin; Nick Haber; Desmond C. Ong. Characterizing Delusional Spirals through Human-LLM Chat Logs. 2026. https://doi.org/10.1145/3805689.3806443
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Characterizing Delusional Spirals through Human-LLM Chat Logs. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-cfc8764b7fdaf5ca5e22a9798e8ba187/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://doi.org/10.1145/3805689.3806443
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.